Evandro Fonseca Junior
b2a06ed994
- Refactored model pull logic to improve error handling and user feedback. - Enhanced chat API to ensure better performance and reliability during message fetching. - Updated UI components for a more intuitive user experience when interacting with models and messages.
20 lines
520 B
JSON
20 lines
520 B
JSON
{
|
|
"model": "nemotron",
|
|
"url": "https://ollama.com/library/nemotron",
|
|
"description": "Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.",
|
|
"variantsCount": 2,
|
|
"variants": [
|
|
{
|
|
"name": "nemotron:latest",
|
|
"size": "43GB",
|
|
"context": "128K",
|
|
"inputType": "Text"
|
|
},
|
|
{
|
|
"name": "nemotron:70b",
|
|
"size": "43GB",
|
|
"context": "128K",
|
|
"inputType": "Text"
|
|
}
|
|
]
|
|
} |